# profilepl

0th

Percentile

##### Profile Maximum Pseudolikelihood

Fits point process models by profile maximum pseudolikelihood

Keywords
models, spatial
##### Usage
profilepl(s, f, ..., rbord = NULL, verbose = TRUE)
##### Arguments
s
Data frame containing values of the irregular parameters over which the profile pseudolikelihood will be computed.
f
Function (such as Strauss) that generates an interpoint interaction object, given the values of the irregular parameters.
...
Data passed to ppm to fit the model.
rbord
Radius for border correction (same for all models). If omitted, this will be computed from the interactions.
verbose
Logical flag indicating whether to print progress reports.
##### Details

The model-fitting function ppm fits point process models to point pattern data. However, only the regular parameters of the model can be fitted by ppm. The model may also depend on irregular parameters that must be fixed in any call to ppm.

This function profilepl is a wrapper which finds the values of the irregular parameters that give the best fit. It uses the method of maximum profile pseudolikelihood.

The argument f would typically be one of the functions Strauss, StraussHard, Softcore, DiggleGratton, Geyer, LennardJones or OrdThresh. For the moment, assume this is so. The argument s must be a data frame whose columns contain values of the irregular parameters. The names of the columns of s must match the argument names of f.

To apply the method of profile maximum pseudolikelihood, each row of s will be taken in turn; the parameter values in this row will be passed to f, resulting in an interaction object. Then ppm will be applied to the data ... using this interaction; this results in a fitted point process model. The value of the log pseudolikelihood from this model is stored. After all rows of s have been processed in this way, the row giving the maximum value of log pseudolikelihood will be found.

The object returned by profilepl contains the profile pseudolikelihood function, the best fitting model, and other data. It can be plotted (yielding a plot of the log pseudolikelihood values against the irregular parameters) or printed (yielding information about the best fitting values of the irregular parameters). In general, f may be any function that will return an interaction object (object of class "interact") that can be used in a call to ppm. Each argument of f must be a single value.

##### Value

• An object of class "profilepl". There are methods for plot and print for this class.

The components of the object include

• fitBest-fitting model
• paramThe data frame s

• profilepl
##### Examples
data(cells)

# one irregular parameter
s <- data.frame(r=seq(0.05,0.15, by=0.01))
<testonly>s <- data.frame(r=c(0.05,0.1,0.15))</testonly>
ps <- profilepl(s, Strauss, cells)
ps
plot(ps)

# two irregular parameters
s <- expand.grid(r=seq(0.05,0.15, by=0.01),sat=1:3)
<testonly>s <- expand.grid(r=c(0.05,0.1,0.15),sat=1:2)</testonly>
pg <- profilepl(s, Geyer, cells)
pg
plot(pg)
pg\$fit
Documentation reproduced from package spatstat, version 1.10-3, License: GPL version 2 or newer

### Community examples

Looks like there are no examples yet.